@tiens.nguyen/gonext-local-worker
v1.0.235
Published
Polls GoNext cloud API for async local LLM jobs and runs them against Ollama/OpenAI-compatible servers on this Mac
Downloads
28,134
Readme
@tiens.nguyen/gonext-local-worker
Run: GONEXT_API_BASE=... GONEXT_WORKER_KEY=... npx -y --package @tiens.nguyen/gonext-local-worker gonext-local-worker
Agent chat mode
Select Agent (instead of Chat) under the composer in the web app. Your
free-form prompt is handed to a smolagents
agent running on your local MLX/Ollama model. The agent can call tools (v1:
http_request) and streams its thinking steps + final answer directly into the
chat thread.
Requires smolagents in the worker's Python environment:
pip install smolagents certificertifisupplies a trusted CA bundle so the agent'shttp_requesttool can verify HTTPS certificates on macOS (where Python's default bundle may be missing). The worker falls back to the system bundle if certifi is absent.- Agent mode is blocked for cloud models (the API returns 400). Select a local MLX or Ollama model first.
- Tool steps appear in the collapsible reasoning (
<think>) area; the final answer is the message body — no new UI needed.
The agent script is gonext_agent_chat.py (reads {messages, agentBaseURL,
agentApiKey, agentModelId, tools, maxSteps} on stdin; emits NDJSON
{"type":"step"/"final","text":"..."} lines on stdout).
API Check / HTTP probe (Tools & Agents modes)
The worker can run Postman-style HTTP probes queued from the web app
("Tools" = tool_only, "Agents" = agentic). The worker always performs the
actual HTTP request itself (Node fetch, so TLS works), measures the
status/latency/headers/body, and classifies it (2xx/3xx/4xx/5xx/timeout/
network_error).
Tools (
tool_only) — no extra setup. The selected local model writes a one-line health summary of the measured result.Agents (
agentic) — a smolagents agent (running on the selected local model) produces the summary. Requirespip install smolagents.The agent talks to your local MLX OpenAI-compatible server (no cloud calls). The agent only summarizes; the worker's measurement stays the source of truth, so if smolagents or the model is unavailable the probe still returns the measured result with a note.
Env vars
GONEXT_PROBE_PYTHON Python executable for smolagents scripts (default: GONEXT_MLX_LM_PYTHON or python3)
